- Hangzhou
Stars
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
Image to prompt with BLIP and CLIP
Heterogeneous AI Computing Virtualization Middleware
Toolkit for linearizing PDFs for LLM datasets/training
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
Cost-efficient and pluggable Infrastructure components for GenAI inference
A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations
Fully open reproduction of DeepSeek-R1
Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
TuGraph: A High Performance Graph Database.
一个轻量级、支持全链路且易于二次开发的大模型应用项目 支持DeepSeek/Qwen2.5等大模型 基于 Dify 、Ollama&Vllm、Sanic 和 Text2SQL 📊 等技术构建的一站式大模型应用开发项目,采用 Vue3、TypeScript 和 Vite 5 打造现代UI。它支持通过 ECharts 📈 实现基于大模型的数据图形化问答,具备处理 CSV 文件 📂 表格问答的能力…
Transformers for Natural Language Processing, published by Packt
Node.js Production Process Manager with a built-in Load Balancer.
A tool which is uses to remove Windows Defender in Windows 8.x, Windows 10 (every version) and Windows 11.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
An Autonomous LLM Agent for Complex Task Solving
A machine learning compiler for GPUs, CPUs, and ML accelerators
Training and serving large-scale neural networks with auto parallelization.
WebUI extension for ControlNet
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration, le…
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Fluss is a streaming storage built for real-time analytics.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
fay是一个帮助数字人(2.5d、3d、移动、pc、网页)或大语言模型(openai兼容、deepseek)连通业务系统的agent框架。